Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/notebook)<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/notebook"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/notebook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp-codebase/notebook"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp-codebase/notebook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00403 |
| Opus 5.5 | $0.00000 | $0.00161 |
| Sonnet 5.5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
notebook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Lab Notebook
Add entries to the lab notebook, view recent entries, or search by tag or keyword.
Instructions
-
Parse $ARGUMENTS for the subcommand:
notebook add "<entry>" [--tag <tag>] [--commit <sha>]— add a timestamped entrynotebook show [--last <n>]— display entries (default: all; --last N for recent)notebook search "<term>"— find entries matching a keyword or tagnotebook timeline— show chronological overview of all entries
-
Add: Run
tools/lab-notebook-manager.sh add "<entry>"with any provided flags. If a research session is active (checkresearch/.session.jsonexists), include the current research question as context. Confirm the entry was added with its timestamp. -
Show: Run
tools/lab-notebook-manager.sh showwith optional--last <n>. Format the output for readability. If no notebook exists, suggest starting a research session first with/research-session start. -
Search: Run
tools/lab-notebook-manager.sh search "<term>". Present matching entries clearly. If no matches, suggest alternative search terms or checking the timeline. -
Timeline: Run
tools/lab-notebook-manager.sh timeline. Display the chronological list with entry count. Useful for getting an overview of research progression. -
If no subcommand given, run
notebook show --last 5as a sensible default. -
Entries should follow good lab notebook practice:
- State what was done, not just what was found
- Include the hypothesis being tested when relevant
- Tag entries for later retrieval (e.g., --tag hypothesis, --tag result, --tag method)
- Link commits when the entry corresponds to a code change
$ARGUMENTS
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 30 lines · 0 tokens per session scan A 96add7f7cc47
notebook is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (7 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 403 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
takeoff
Create, resume, or clear a session hand-off baton (one per work line).
generate-command
Génération Commande Symfony.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
b-animate-dev
Animate and model-check a B machine with probcli.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.